Exercise of self-adaptive physics informed neural network (https://arxiv.org/pdf/2009.04544.pdf). In this example, Laplace's equation is solved in 2-D for Dirichlet boundary conditions. Imposing large initial weights for BC loss is needed for satisfactory convergence. For a general class of solutions, you should try to use TensorDiffEq (https://tensordiffeq.io).
-
Notifications
You must be signed in to change notification settings - Fork 0
suyong-choi/AdaptivePINN
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Exercise adaptive physics informed neural network (aPINN)
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published